© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32319
    Prev
    Next
    INDEX
    Explanations

    division by 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīåĽ°éļ¾
    -0.07
    áĢ½
    -0.06
    å¸Īé£İ
    -0.06
    stial
    -0.06
    ARED
    -0.06
    _MAY
    -0.06
    áĢķáĢº
    -0.06
    ÙĨج
    -0.06
    nist
    -0.06
    åħ¶ä¸Ģ
    -0.06
    POSITIVE LOGITS
    emens
    0.08
    iblings
    0.08
     báu
    0.07
    ä¸įèĩ³
    0.07
    avid
    0.07
    cales
    0.07
    resent
    0.07
    zeug
    0.07
    cad
    0.07
    ropolit
    0.07
    Activations Density 0.003%

    No Known Activations